13 papers
MYOPIA: Understanding the Limits of Tree-Based Reasoning in Vision-Language Models
Islam Mesabah, Sary Elmansoury, Gerrit Großmann +2
Decision trees can make vision-language model (VLM) classification interpretable by replacing a single prediction with a sequence of root-to-leaf questions. However, the accuracy c…
Accounting for Bias Enables Sustainable LLM Evaluation
Harshita Katoch, David Antony Selby, Gerrit Großmann +1
LLM-as-a-judge has become the de facto standard for scalable, subjective evaluation, yet current leaderboards compensate for systematic measurement bias by running ever more compar…
CLAM: Causal Spatial Disaggregation to Infer Local Effects From Coarse Data
Gerrit Großmann, Sumantrak Mukherjee, Sebastian J. Vollmer
Learning fine-grained spatial patterns from coarse-resolution data is challenging, especially in causal settings where high-resolution effects must be inferred from aggregated inte…
Orca: Neural Operators for Causal Reasoning in Continuous Time
Gerrit Großmann, David A. Selby, Sebastian J. Vollmer
Structural causal models are the standard language for reasoning about interventions and counterfactuals, but they describe static variables, typically measured once, and usually f…
When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting
Yahya Aalaila, Mouad Elhamdi, Gerrit Großmann +3
Spatio-temporal point-process models must often generalise across space when local event histories are sparse. We study whether exogenous spatial context can compensate in such reg…
MEDAKA: Construction of Biomedical Knowledge Graphs Using Large Language Models
Asmita Sengupta, David Antony Selby, Sebastian Josef Vollmer +1
Knowledge graphs (KGs) are increasingly used to represent biomedical information in structured, interpretable formats. However, existing biomedical KGs often focus narrowly on mole…
Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs
Sary Elmansoury, Islam Mesabah, Gerrit Großmann +4
Vision language models (VLMs) excel at zero-shot visual classification, but their performance on fine-grained tasks and large hierarchical label spaces is understudied. This paper…
BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation
Yujing Ke, Kevin George, Kathan Pandya +5
Identifying novel hypotheses is essential to scientific research, yet this process risks being overwhelmed by the sheer volume and complexity of available information. Existing aut…
The Power of Stories: Narrative Priming Shapes How LLM Agents Collaborate and Compete
Gerrit Großmann, Larisa Ivanova, Sai Leela Poduru +4
According to Yuval Noah Harari, large-scale human cooperation is driven by shared narratives that encode common beliefs and values. This study explores whether such narratives can…
When Counterfactual Reasoning Fails: Chaos and Real-World Complexity
Yahya Aalaila, Gerrit Großmann, Sumantrak Mukherjee +2
Counterfactual reasoning, a cornerstone of human cognition and decision-making, is often seen as the 'holy grail' of causal learning, with applications ranging from interpreting ma…
Neural Spatiotemporal Point Processes: Trends and Challenges
Sumantrak Mukherjee, Mouad Elhamdi, George Mohler +4
Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibit intricate dependencies and he…
CleanSurvival: Automated data preprocessing for time-to-event models using reinforcement learning
Yousef Koka, David Selby, Gerrit Großmann +2
Data preprocessing is often paid little attention in machine learning, despite its potentially significant impact on model performance. While automated machine learning pipelines a…
icon: Fast Simulation of Epidemics on Coevolving Networks
Gerrit Großmann, Sebastian Vollmer
We introduce a fast simulation technique for modeling epidemics on adaptive networks. Our rejection-based algorithm efficiently simulates the co-evolution of the network structure…